CN114707266A - Industrial centrifugal pump operation stability prediction system based on artificial intelligence - Google Patents
Industrial centrifugal pump operation stability prediction system based on artificial intelligence Download PDFInfo
- Publication number
- CN114707266A CN114707266A CN202210334447.7A CN202210334447A CN114707266A CN 114707266 A CN114707266 A CN 114707266A CN 202210334447 A CN202210334447 A CN 202210334447A CN 114707266 A CN114707266 A CN 114707266A
- Authority
- CN
- China
- Prior art keywords
- flow
- rotor
- centrifugal pump
- abnormal
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Fluid Mechanics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Algebra (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computational Mathematics (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
- Control Of Non-Positive-Displacement Pumps (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an artificial intelligence-based prediction system for the running stability of an industrial centrifugal pump, which can be used as an artificial intelligence system and an artificial intelligence optimization operation system in the industrial production field when being applied specifically, can be used for developing application software such as computer vision software and the like, utilizes electronic equipment to carry out data identification, and acquires data information through an information acquisition module; evaluating the abnormal degree of the rotor through a rotor abnormal degree evaluation module; acquiring a flow abnormity index through a flow abnormity degree evaluation module according to the ratio of the liquid quality to the pump body quality, the change of outlet flow and the abnormity degree of the rotor; correcting the flow abnormity index to obtain the flow abnormity degree; the stability prediction module is used for predicting the future flow abnormal degree and judging whether the centrifugal pump runs stably, so that the working state of the centrifugal pump can be identified by using electronic equipment, the stability of the centrifugal pump can be predicted, and the abnormal condition can be monitored in time.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an artificial intelligence-based prediction system for the operation stability of an industrial centrifugal pump.
Background
Centrifugal pumps are pumps that transport liquids by centrifugal force generated when an impeller rotates. For an industrial centrifugal pump, the unstable operation capacity easily damages the structure of the centrifugal pump, which reduces the service life or damages the centrifugal pump. If the centrifugal pump is in abnormal failure, a series of chain effects may be caused, which causes serious consequences, and therefore, the operation stability and reliability of the centrifugal pump need to be ensured.
The unstable reason of centrifugal pump operation is various, and the centrifugal pump work difference of different models is also great, and the detection to centrifugal pump operation stability relies on the standard of commonality at present, leads to the rate of accuracy not high, appears misjudgement and miss judgement easily, brings unnecessary cost of labor and has higher application risk. With the development of artificial intelligence systems in the field of industrial production, an artificial intelligence system capable of predicting the working reliability of a centrifugal pump needs to be provided, so that the continuity and reliability of production are guaranteed.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an artificial intelligence-based prediction system for the operation stability of an industrial centrifugal pump, and the adopted technical scheme is as follows:
one embodiment of the invention provides an artificial intelligence-based system for predicting the operation stability of an industrial centrifugal pump, which comprises the following modules:
the information acquisition module is used for acquiring vibration information of the rotor, the rotating speed of the rotor, the flow rate of an outlet of the centrifugal pump and the mass of liquid in a cavity of the centrifugal pump in real time, and acquiring the support rigidity of a rotor structure, the natural frequency of the rotor and the mass of a pump body of the centrifugal pump;
the rotor abnormal degree evaluation module is used for evaluating the abnormal degree of the rotor according to the support rigidity, the rotating speed, the natural frequency of the rotor and the vibration information difference of adjacent moments;
the flow abnormal degree evaluation module is used for taking the product of the cross section area and the flow speed of the outlet of the centrifugal pump as outlet flow, and acquiring a flow abnormal index according to the ratio of the liquid mass to the pump body mass, the change of the outlet flow and the abnormal degree of the rotor; acquiring standard flow abnormality indexes at different rotating speeds, calculating a correction coefficient of the standard flow abnormality indexes corresponding to the rotating speeds, and correcting the flow abnormality indexes by using the correction coefficient to acquire flow abnormality degrees;
and the stability prediction module is used for predicting the future flow abnormal degree by using the historical flow abnormal degree data and judging whether the centrifugal pump runs stably according to the future flow abnormal degree.
Preferably, the information acquisition module includes:
the vibration information acquisition unit is used for acquiring left and right vibration data of the rotor in the horizontal direction and upper and lower vibration data of the rotor in the vertical direction in real time, further acquiring a vibration vector of the horizontal direction and a vibration vector of the vertical direction, and performing vector superposition on the two vibration vectors to obtain a space vibration vector as real-time vibration information.
Preferably, the information collecting module further includes:
and the rotating speed acquisition unit is used for acquiring the rotating speed of the rotor through a photoelectric sensor or detecting the rotating speed of the rotor through a rotary encoder.
Preferably, the rotor abnormality degree evaluation module includes:
the rotor abnormal degree calculating unit is used for converting the rotating speed into rotating frequency, acquiring the frequency difference between the rotating frequency and the natural frequency of the rotor, and obtaining the resonance degree by taking the ratio of the rotating speed to the frequency difference as the index of the rotating speed; and acquiring the vector difference of the vibration information at adjacent moments, and calculating the product of the ratio of the resonance degree and the vector difference and the supporting rigidity, namely the abnormal degree of the rotor.
Preferably, the rotor abnormality degree evaluation module further includes:
and the rotor abnormal degree correcting unit is used for acquiring the radius of the impeller as a correction coefficient to correct the rotor abnormal degree.
Preferably, the flow abnormality degree evaluation module includes:
and the outlet flow obtaining unit is used for collecting a flow velocity sequence formed by a plurality of flow velocities in a preset time before the current moment and the current flow velocity, carrying out median filtering on the flow velocity sequence, obtaining the filtered average flow velocity as the optimized flow velocity at the current moment, and taking the product of the optimized flow velocity and the cross sectional area as the outlet flow.
Preferably, the flow abnormality degree evaluation module further includes:
and the flow abnormal index correcting unit is used for acquiring the ratio of the standard abnormal index under each rotating speed to the average abnormal index under the corresponding rotating speed as a correction coefficient under the rotating speed, performing function fitting on the correction coefficients under different rotating speeds, acquiring the correction coefficient under the rotating speed corresponding to the current flow abnormal index by using the function fitting result, and taking the product of the current flow abnormal index and the corresponding correction coefficient as the current flow abnormal degree.
Preferably, the stability prediction module comprises:
and the future flow abnormal degree prediction unit is used for inputting the historical flow abnormal degree into the prediction neural network and outputting the predicted future flow abnormal degree.
Preferably, the stability prediction module further comprises:
the running state judging unit is used for acquiring a difference value of the abnormal degrees of the historical flow at adjacent moments, and when the difference value is larger than a first threshold value, the running state of the centrifugal pump at the corresponding moment is unstable; and when the future flow abnormal degree of the target moment is greater than a second threshold value and the average abnormal degree of the plurality of future flow abnormal degrees in the preset time before the target moment is also greater than the second threshold value, the operating state of the centrifugal pump at the target moment is unstable.
The embodiment of the invention at least has the following beneficial effects:
acquiring a flow abnormity index through a flow abnormity degree evaluation module according to the ratio of the liquid quality to the pump body quality, the change of outlet flow and the abnormity degree of the rotor; correcting the flow abnormality index according to the standard flow abnormality index to obtain the flow abnormality degree; and predicting the abnormal degree of the future flow through a stability prediction module, and judging whether the centrifugal pump operates stably. The embodiment of the invention can be used for identifying the working state of the centrifugal pump by using the electronic equipment, predicting the stability of the centrifugal pump, monitoring abnormal conditions in time and being applied to an artificial intelligent optimization operation system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a system block diagram of an artificial intelligence-based system for predicting the operational stability of an industrial centrifugal pump according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following detailed description of the system for predicting the operation stability of an industrial centrifugal pump based on artificial intelligence according to the present invention, its specific implementation, structure, features and effects will be provided in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the artificial intelligence-based industrial centrifugal pump operation stability prediction system in detail with reference to the accompanying drawings.
Referring to fig. 1, a system block diagram of an artificial intelligence based industrial centrifugal pump operation stability prediction system according to an embodiment of the present invention is shown, the system includes the following modules:
the system comprises an information acquisition module 100, a rotor abnormal degree evaluation module 200, a flow abnormal degree evaluation module 300 and a stability prediction module 400.
The information acquisition module 100 is configured to acquire vibration information of the rotor, a rotation speed of the rotor, a flow rate of an outlet of the centrifugal pump, and a mass of liquid in a cavity of the centrifugal pump in real time, and acquire support stiffness of a rotor structure, an inherent frequency of the rotor, and a mass of a pump body of the centrifugal pump.
Specifically, the information acquisition module 100 includes a vibration information acquisition unit 110, a rotational speed acquisition unit 120, a flow rate acquisition unit 130, a mass acquisition unit 140, and a rotor data acquisition unit 150.
The vibration information acquisition unit 110 is configured to acquire two pieces of vibration data of the left and right sides of the rotor in the horizontal direction and two pieces of vibration data of the upper and lower sides of the rotor in the vertical direction in real time, further acquire a vibration vector of the horizontal direction and a vibration vector of the vertical direction, and perform vector superposition on the two vibration vectors to obtain a spatial vibration vector as real-time vibration information.
The vibration sensor is located the outside of centrifugal pump, and the shell evenly distributed in the outside of centrifugal pump rotor position has 4 sensors to gather information jointly. The 4 vibration sensors are respectively positioned on the upper, lower, left and right sides of the cylindrical shell to form space vectors. The acquisition frequency was 20 ms. The readings of the upper, lower, left and right sensors are respectively assigned to D1、D2、D3、D4。D1-D2As a vertical component; d4-D3As a horizontal component, the two components are vector-superimposed to obtain a final vibration vector D, and the vibration vector D is stored in terms of time D ═ D { (D)1,D2…,Dt,…,DTAnd acquiring every 20ms to obtain T vibration vectors, and performing median filtering on a sequence formed by the vibration vectors.
A rotation speed obtaining unit 120 for obtaining the rotation speed of the rotor through a photoelectric sensor or detecting the rotation speed of the rotor through a rotary encoder.
And the flow rate acquisition unit 130 is used for acquiring the flow rate at the outlet through the flow rate sensor, and acquiring the flow rate once every 50ms to obtain a plurality of flow rates V.
A mass acquisition unit 140 for acquiring weight information W at the bottom of the hydraulic pump at 50ms intervals by using the pressure sensor due to the pump body mass W of the centrifugal pumpPump and method of operating the sameThe mass is known, so that the mass W of the liquid in the current chamber can be obtainedLiquid for treating urinary tract infection＝W-WPump. Before the centrifugal pump works normally, the pump shell and the water suction pipe are filled with liquid, then the motor is started, the pump shaft drives the impeller and the liquid to rotate at a high speed, and the liquid is thrown to the outer edge of the impeller and flows into a pipeline of the centrifugal pump through a flow channel of the volute pump shell. The higher the density of the liquid delivered by the centrifugal pump, the heavier the mass of the liquid in the cavity, the heavier the load on the rotor and the pump body thereof, and the higher the pressure on the supporting structure, which is more likely to cause vibration and damage stability.
And a rotor data acquisition unit 150 for acquiring the support stiffness and natural frequency of the rotor.
The supporting rigidity of each centrifugal pump is a fixed value and is determined by a fixed rotor structure, the larger the supporting rigidity is, the better the stability is, and the supporting rigidity Z of the rotor is obtained.
The natural frequency of the centrifugal pump rotor is determined by the mechanical structure and material, and the natural frequency D of the rotor is obtained0。
And the rotor abnormal degree evaluation module 200 is used for evaluating the abnormal degree of the rotor according to the support rigidity, the rotating speed, the natural frequency of the rotor and the vibration information difference of adjacent moments.
Specifically, the rotor abnormality degree evaluation module 200 includes a rotor abnormality degree calculation unit 210 and a rotor abnormality degree correction unit 220.
A rotor abnormality degree calculation unit 210 for converting the rotation speed into a rotation frequency, acquiring a frequency difference between the rotation frequency and a natural frequency of the rotor, and obtaining a resonance degree by using a ratio of the rotation speed to the frequency difference as an index of the rotation speed; and acquiring the vector difference of the vibration information at adjacent moments, and calculating the product of the ratio of the resonance degree and the vector difference and the supporting rigidity, namely the abnormal degree of the rotor.
The main reason for causing the vibration of the whole centrifugal pump is the vibration of the internal rotor, and if the vibration frequency caused by the rotation of the rotor is close to the natural vibration frequency of the rotor, the resonance degree is aggravated, and the stability of the centrifugal pump is damaged.
Acquiring the resonance degree of the rotor:
wherein Re represents the degree of rotor resonance, R represents the rotation speed of the rotor,
indicating the rotational frequency of the speed conversion, D0Representing the natural frequency of the rotor.
And (3) calculating the abnormal degree of the rotor:
wherein M represents the abnormal degree of the rotor, Z represents the supporting rigidity of the rotor, DtRepresents the t-th vibration information, Dt-1Represents the t-1 st vibration information, | Dt-Dt-1And | represents a modulo length of a vector difference of the t-th vibration information and the previous vibration information.
The larger the rotor resonance degree is, the more easily the centrifugal pump is damaged; the larger the difference between the vibration information at the adjacent times is, the more serious the vibration of the rotor at the time corresponding to the tth vibration information is, and the more likely the abnormality of the rotor occurs.
And a rotor abnormality degree correcting unit 220 for acquiring the radius of the impeller as a correction coefficient to correct the abnormality degree of the rotor.
And acquiring the radius C of an impeller of the centrifugal pump to correct the abnormal degree of the rotors of the centrifugal pumps of different models, and constraining the abnormal degree of the rotors in a normal range, wherein the corrected abnormal degree of the rotors is U (C multiplied by M), and the abnormal degree U of the rotors is calculated every 20 ms.
The flow abnormal degree evaluation module 300 is used for taking the product of the cross section area and the flow speed of the centrifugal pump outlet as outlet flow, and acquiring a flow abnormal index according to the ratio of the liquid mass to the pump body mass, the change of the outlet flow and the abnormal degree of the rotor; and acquiring standard flow abnormality indexes at different rotating speeds, calculating a correction coefficient of the standard flow abnormality indexes corresponding to the rotating speeds, and correcting the flow abnormality indexes by using the correction coefficient to acquire the flow abnormality degree.
Specifically, the flow abnormality degree evaluation module 300 includes an outlet flow obtaining unit 310, a flow abnormality index calculating unit 320, and a flow abnormality index correcting unit 330.
An outlet flow rate obtaining unit 310, configured to take the product of the cross-sectional area and the flow rate of the centrifugal pump outlet as the outlet flow rate.
The method for calculating the outlet flow comprises the following steps: q ═ sxv, where Q denotes the outlet flow.
Preferably, a flow velocity sequence is formed by collecting a plurality of flow velocities in a preset time before the current moment and the current flow velocity, median filtering is performed on the flow velocity sequence, the average flow velocity after filtering is obtained and used as the optimized flow velocity at the current moment, and the product of the optimized flow velocity and the cross-sectional area is used as the outlet flow.
As an example, the preset time is 1 second in the embodiment of the present invention.
The flow anomaly index calculation unit 320 acquires a flow anomaly index according to the ratio of the liquid mass to the pump body mass, the change of the outlet flow and the anomaly degree of the rotor.
First the change in outlet flow is obtained: the flow rate is collected once every 50ms, 20 flow rates are collected every second, the optimized flow rate of each flow rate is obtained by the method in the outlet flow obtaining unit 310, the standard deviation std (q) of a group of 5 optimized flow rates is calculated, and 4 standard deviations are obtained every second to reflect the change of the outlet flow rate.
Calculating a flow anomaly index:
where P represents a flow anomaly index.
4 standard deviations STD (Q) are obtained every second, but one rotor abnormal degree U is obtained every 20ms, so when the flow abnormal index P is calculated, the latest rotor abnormal degree U updated at the moment corresponding to the standard deviations STD (Q) is selected for calculation, and 4 flow abnormal indexes P are obtained every second.
The flow abnormality index correction unit 330 is configured to, for each standard abnormality index at each rotation speed, obtain a ratio of the standard abnormality index to an average abnormality index at a corresponding rotation speed as a correction coefficient at the rotation speed, perform function fitting on the correction coefficients at different rotation speeds, obtain a correction coefficient at a rotation speed corresponding to a current flow abnormality index by using a function fitting result, and use a product of the current flow abnormality index and the corresponding correction coefficient as a current flow abnormality degree.
The centrifugal pump is respectively driven to work for a long time at different rotating speeds under experimental conditions, as an example, in the embodiment of the invention, the sampling rotating speed is 2500r/min, 3000r/min, 3500r/min, 4000r/min and 4500r/min, a plurality of abnormal indexes are obtained under each rotating speed, the average value of the abnormal indexes is taken as the standard abnormal index under the rotating speed, the average value of a plurality of flow abnormal indexes under the same rotating speed calculated in the modules is simultaneously obtained, the ratio of the standard abnormal index to the average value under the corresponding rotating speed is taken as the correction coefficient under the rotating speed, the correction coefficients under a plurality of rotating speeds are obtained, the correction coefficients under different rotating speeds are subjected to function fitting to obtain the correction coefficients between different rotating speeds and flow abnormal indexes, the correction coefficients are multiplied by the calculated flow abnormal indexes to correct the flow abnormal indexes, the degree of flow anomaly is obtained.
And the stability prediction module 400 is used for predicting the future flow abnormal degree by using the historical flow abnormal degree data and judging whether the centrifugal pump runs stably according to the future flow abnormal degree.
Specifically, the stability prediction module 400 includes a future flow abnormality degree prediction unit 410 and an operation state judgment unit 420.
And a future flow anomaly degree prediction unit 410, configured to input the historical flow anomaly degree into the prediction neural network, and output the predicted future flow anomaly degree.
And training the prediction neural network by using a large amount of data of abnormal degree of flow acquired historically until the loss function is converged to obtain the trained prediction neural network. Predicting the future flow abnormal degree at the next moment by using a prediction neural network
As an example, the predictive neural network in the embodiment of the present invention uses a Recurrent Neural Network (RNN), and in other embodiments, other predictive neural networks that can achieve the same effect, such as a Time Convolution Network (TCN), an LSTM network, and the like, may also be used.
The operation state judgment unit 420 is configured to obtain a difference value of the abnormal degrees of the historical flow at adjacent moments, and when the difference value is greater than a first threshold, the operation state of the centrifugal pump at the corresponding moment is unstable; and acquiring the future flow abnormal degree of the target moment and the average abnormal degree of a plurality of future flow abnormal degrees within preset time before the target moment, wherein when the future flow abnormal degree of the target moment is greater than a second threshold value and the average abnormal degree is also greater than the second threshold value, the running state of the centrifugal pump at the target moment is unstable.
When the difference value | delta P | of the known abnormal degree of the flow at the adjacent time is larger than the first threshold value C1In time, it is described that liquid in the hydraulic pump cavity is not abundant, air or other foreign matters exist, the operation state of the centrifugal pump at the corresponding moment is unstable, and abnormal early warning needs to be performed.
Degree of future flow anomaly at target time
Greater than a second threshold value C2Then, the average abnormal degree of a plurality of future flow abnormal degrees in preset time before the target moment is obtained, and when the average abnormal degree is also larger than a second threshold value C at the same time2When the pressure at the target moment exceeds the load, long-time overload operation may reduce the service life of the centrifugal pump, and the rotating speed of the rotor needs to be reducedAnd protecting the pump body.
As an example, the first threshold value C in the embodiment of the present invention1Value 60, second threshold value C2The value is 40 and the preset time is also 1 second.
The method for reducing the rotating speed can adopt a step speed reduction method, and the rotating speed reduced by 5 percent in a step shape plays a role in protection; linear deceleration may be performed, and a desired rotation speed may be obtained from the desired P by using the relationship between the rotation speed and the degree of abnormality in the flow rate
To be provided with
And inputting the PID regulation closed loop as an input quantity to control the linear and soft reduction of the rotating speed to meet the standard of stability P.
In summary, the embodiment of the present invention includes the following modules:
the system comprises an information acquisition module 100, a rotor abnormal degree evaluation module 200, a flow abnormal degree evaluation module 300 and a stability prediction module 400.
Specifically, the information acquisition module 100 acquires vibration information of the rotor, the rotating speed of the rotor, the flow rate of an outlet of the centrifugal pump and the mass of liquid in a cavity of the centrifugal pump in real time to acquire the support rigidity of the rotor structure, the natural frequency of the rotor and the mass of a pump body of the centrifugal pump; the abnormal degree of the rotor is evaluated by a rotor abnormal degree evaluation module 200 according to the support rigidity, the rotating speed, the natural frequency of the rotor and the vibration information difference of adjacent moments; the product of the cross section area and the flow velocity of the outlet of the centrifugal pump is used as the outlet flow through the flow abnormal degree evaluation module 300, and a flow abnormal index is obtained according to the ratio of the liquid mass to the pump body mass, the change of the outlet flow and the abnormal degree of the rotor; acquiring standard flow abnormality indexes at different rotating speeds, calculating a correction coefficient of the standard flow abnormality indexes corresponding to the rotating speeds, and correcting the flow abnormality indexes by using the correction coefficient to acquire flow abnormality degrees; the stability prediction module 400 predicts the future flow abnormal degree by using the historical flow abnormal degree data, and judges whether the centrifugal pump operates stably according to the future flow abnormal degree. The embodiment of the invention relates to an artificial intelligence system in the field of industrial production, which can be applied to an electronic device for identifying the working state of a centrifugal pump, is applied to an artificial intelligence optimization operation system for predicting the stability of the centrifugal pump, can timely monitor the abnormal condition of the centrifugal pump and avoid great loss.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present application, and they should be construed as being included in the present application.
Claims (9)
1. The system for predicting the operation stability of the industrial centrifugal pump based on artificial intelligence is characterized by comprising the following modules:
the information acquisition module is used for acquiring vibration information of the rotor, the rotating speed of the rotor, the flow rate of an outlet of the centrifugal pump and the mass of liquid in a cavity of the centrifugal pump in real time, and acquiring the support rigidity of a rotor structure, the natural frequency of the rotor and the mass of a pump body of the centrifugal pump;
the rotor abnormal degree evaluation module is used for evaluating the abnormal degree of the rotor according to the support rigidity, the rotating speed, the natural frequency of the rotor and the vibration information difference of adjacent moments;
the flow abnormal degree evaluation module is used for taking the product of the cross section area and the flow speed of the outlet of the centrifugal pump as outlet flow, and acquiring a flow abnormal index according to the ratio of the liquid mass to the pump body mass, the change of the outlet flow and the abnormal degree of the rotor; acquiring standard flow abnormality indexes at different rotating speeds, calculating a correction coefficient of the standard flow abnormality indexes corresponding to the rotating speeds, and correcting the flow abnormality indexes by using the correction coefficient to acquire flow abnormality degrees;
and the stability prediction module is used for predicting the future flow abnormal degree by utilizing the historical flow abnormal degree data and judging whether the centrifugal pump operates stably according to the future flow abnormal degree.
2. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the information collection module comprises:
the vibration information acquisition unit is used for acquiring left and right vibration data of the rotor in the horizontal direction and upper and lower vibration data of the rotor in the vertical direction in real time, further acquiring a vibration vector of the horizontal direction and a vibration vector of the vertical direction, and performing vector superposition on the two vibration vectors to obtain a space vibration vector as real-time vibration information.
3. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the information collection module further comprises:
and the rotating speed acquisition unit is used for acquiring the rotating speed of the rotor through a photoelectric sensor or detecting the rotating speed of the rotor through a rotary encoder.
4. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the rotor anomaly assessment module comprises:
the rotor abnormal degree calculating unit is used for converting the rotating speed into rotating frequency, acquiring the frequency difference between the rotating frequency and the natural frequency of the rotor, and obtaining the resonance degree by taking the ratio of the rotating speed to the frequency difference as the index of the rotating speed; and obtaining the vector difference of the vibration information at adjacent moments, and calculating the product of the ratio of the resonance degree and the vector difference and the supporting rigidity, namely the abnormal degree of the rotor.
5. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the rotor anomaly assessment module further comprises:
and the rotor abnormal degree correcting unit is used for acquiring the radius of the impeller as a correction coefficient to correct the rotor abnormal degree.
6. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the flow anomaly assessment module comprises:
and the outlet flow obtaining unit is used for collecting a flow velocity sequence formed by a plurality of flow velocities in a preset time before the current moment and the current flow velocity, carrying out median filtering on the flow velocity sequence, obtaining the filtered average flow velocity as the optimized flow velocity at the current moment, and taking the product of the optimized flow velocity and the cross sectional area as the outlet flow.
7. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the flow anomaly assessment module further comprises:
and the flow abnormal index correcting unit is used for acquiring the ratio of the standard abnormal index under each rotating speed to the average abnormal index under the corresponding rotating speed as a correction coefficient under the rotating speed, performing function fitting on the correction coefficients under different rotating speeds, acquiring the correction coefficient under the rotating speed corresponding to the current flow abnormal index by using the function fitting result, and taking the product of the current flow abnormal index and the corresponding correction coefficient as the current flow abnormal degree.
8. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the stability prediction module comprises:
and the future flow abnormal degree prediction unit is used for inputting the historical flow abnormal degree into the prediction neural network and outputting the predicted future flow abnormal degree.
9. The artificial intelligence based industrial centrifugal pump operational stability prediction system of claim 1, wherein the stability prediction module further comprises:
the running state judging unit is used for acquiring a difference value of the abnormal degrees of the historical flow at adjacent moments, and when the difference value is larger than a first threshold value, the running state of the centrifugal pump at the corresponding moment is unstable; and acquiring the future flow abnormal degree of the target moment and the average abnormal degree of a plurality of future flow abnormal degrees within preset time before the target moment, wherein when the future flow abnormal degree of the target moment is greater than a second threshold value and the average abnormal degree is also greater than the second threshold value, the running state of the centrifugal pump at the target moment is unstable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210334447.7A CN114707266B (en) | 2022-03-31 | 2022-03-31 | Industrial centrifugal pump operation stability prediction system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210334447.7A CN114707266B (en) | 2022-03-31 | 2022-03-31 | Industrial centrifugal pump operation stability prediction system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114707266A true CN114707266A (en) | 2022-07-05 |
| CN114707266B CN114707266B (en) | 2023-04-21 |
Family
ID=82171248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210334447.7A Active CN114707266B (en) | 2022-03-31 | 2022-03-31 | Industrial centrifugal pump operation stability prediction system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114707266B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114934898A (en) * | 2022-07-25 | 2022-08-23 | 启东市申力高压油泵厂 | Hydraulic pump fault diagnosis analysis system based on multi-mode parameters |
| CN115033042A (en) * | 2022-08-10 | 2022-09-09 | 启东亦大通自动化设备有限公司 | Food hydroextractor intelligence control system based on multimode thing networking |
| CN115090378A (en) * | 2022-08-26 | 2022-09-23 | 启东市春晨机械有限公司 | Abnormal vibration monitoring and early warning method for hammer head rotor of metal crusher |
| CN115144399A (en) * | 2022-08-30 | 2022-10-04 | 吉林省信息技术研究所 | Assembly quality detection method and device based on machine vision |
| CN117329135A (en) * | 2023-10-13 | 2024-01-02 | 山东中探机械有限公司 | Method for monitoring running state of slurry pump based on data analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5914875A (en) * | 1996-01-11 | 1999-06-22 | Kabushiki Kaisha Toshiba | Method and apparatus for diagnosing plant anomaly |
| JP3068091B1 (en) * | 1999-06-02 | 2000-07-24 | 核燃料サイクル開発機構 | Fault diagnosis device |
| US20080294382A1 (en) * | 2007-05-21 | 2008-11-27 | Samsung Electronics Co., Ltd. | Method and apparatus for pump fault prediction |
| CN104866704A (en) * | 2015-03-21 | 2015-08-26 | 北京化工大学 | Method for evaluating state of centrifugal pump on basis of fuzzy comprehensive evaluation |
| CN111259717A (en) * | 2019-10-21 | 2020-06-09 | 杭州安脉盛智能技术有限公司 | Method and system for judging abnormal state of rotating equipment |
| CN111581889A (en) * | 2020-05-26 | 2020-08-25 | 瑞纳智能设备股份有限公司 | Fault prediction method, system and equipment for heating equipment assembly |
| CN112329357A (en) * | 2020-10-29 | 2021-02-05 | 湘潭大学 | Simple diagnosis method and system for vibration fault of clean water centrifugal pump |
| CN112785091A (en) * | 2021-03-04 | 2021-05-11 | 湖北工业大学 | Method for performing fault prediction and health management on oil field electric submersible pump |
| CN113156917A (en) * | 2021-04-10 | 2021-07-23 | 河南巨捷电子科技有限公司 | Power grid equipment fault diagnosis method and system based on artificial intelligence |
-
2022
- 2022-03-31 CN CN202210334447.7A patent/CN114707266B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5914875A (en) * | 1996-01-11 | 1999-06-22 | Kabushiki Kaisha Toshiba | Method and apparatus for diagnosing plant anomaly |
| JP3068091B1 (en) * | 1999-06-02 | 2000-07-24 | 核燃料サイクル開発機構 | Fault diagnosis device |
| US20080294382A1 (en) * | 2007-05-21 | 2008-11-27 | Samsung Electronics Co., Ltd. | Method and apparatus for pump fault prediction |
| CN104866704A (en) * | 2015-03-21 | 2015-08-26 | 北京化工大学 | Method for evaluating state of centrifugal pump on basis of fuzzy comprehensive evaluation |
| CN111259717A (en) * | 2019-10-21 | 2020-06-09 | 杭州安脉盛智能技术有限公司 | Method and system for judging abnormal state of rotating equipment |
| CN111581889A (en) * | 2020-05-26 | 2020-08-25 | 瑞纳智能设备股份有限公司 | Fault prediction method, system and equipment for heating equipment assembly |
| CN112329357A (en) * | 2020-10-29 | 2021-02-05 | 湘潭大学 | Simple diagnosis method and system for vibration fault of clean water centrifugal pump |
| CN112785091A (en) * | 2021-03-04 | 2021-05-11 | 湖北工业大学 | Method for performing fault prediction and health management on oil field electric submersible pump |
| CN113156917A (en) * | 2021-04-10 | 2021-07-23 | 河南巨捷电子科技有限公司 | Power grid equipment fault diagnosis method and system based on artificial intelligence |
Non-Patent Citations (6)
| Title |
|---|
| CHANGTIAN YING等: "a time series data cleaning framework based on lstm prediction model for pumped storage", 《FOREST CHEMICALS》 * |
| SUPRIYA GUPTA等: "Applying big data analytics to detect，diagnose，and prevent impending failures in electric submersible pumps", 《SPE ANNUAL TECHNICAL CONFERENCE AND EXHIBITION》 * |
| 何金焕: "基于概率神经网络的液压泵故障诊断", 《农家参谋》 * |
| 刘亚昆等: "火电厂给水泵振动原因分析及处理", 《沈阳工程学院学报(自然科学版)》 * |
| 孙毅等: "向家坝电站运行设备异常状态识别功能的设计与实现", 《西北水电》 * |
| 宋小伍等: "一种离心泵在小流量下振动异常的分析与处理", 《水泵技术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114934898A (en) * | 2022-07-25 | 2022-08-23 | 启东市申力高压油泵厂 | Hydraulic pump fault diagnosis analysis system based on multi-mode parameters |
| CN114934898B (en) * | 2022-07-25 | 2022-10-21 | 启东市申力高压油泵厂 | Hydraulic pump fault diagnosis analysis system based on multi-mode parameters |
| CN115033042A (en) * | 2022-08-10 | 2022-09-09 | 启东亦大通自动化设备有限公司 | Food hydroextractor intelligence control system based on multimode thing networking |
| CN115033042B (en) * | 2022-08-10 | 2023-10-20 | 微山县恒信食品有限公司 | Intelligent control system of food dehydrator based on multi-mode Internet of things |
| CN115090378A (en) * | 2022-08-26 | 2022-09-23 | 启东市春晨机械有限公司 | Abnormal vibration monitoring and early warning method for hammer head rotor of metal crusher |
| CN115144399A (en) * | 2022-08-30 | 2022-10-04 | 吉林省信息技术研究所 | Assembly quality detection method and device based on machine vision |
| CN115144399B (en) * | 2022-08-30 | 2023-01-13 | 吉林省信息技术研究所 | Assembly quality detection method and device based on machine vision |
| CN117329135A (en) * | 2023-10-13 | 2024-01-02 | 山东中探机械有限公司 | Method for monitoring running state of slurry pump based on data analysis |
| CN117329135B (en) * | 2023-10-13 | 2024-04-05 | 山东中探机械有限公司 | Method for monitoring running state of slurry pump based on data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114707266B (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114707266A (en) | Industrial centrifugal pump operation stability prediction system based on artificial intelligence | |
| US9324037B2 (en) | Method for monitoring of rotating machines | |
| EP2609326B1 (en) | Method of operating a wind turbine and wind turbine | |
| EP3088733B1 (en) | Method for operating a wind turbine based on degradation of wind turbine blade | |
| US7099852B2 (en) | Detection of pump cavitation/blockage and seal failure via current signature analysis | |
| EP1978223B1 (en) | Determining bleed valve failures in gas turbine engines | |
| CN110830943A (en) | Equipment state monitoring system based on edge calculation and big data analysis | |
| EP2103915B1 (en) | Apparatus and method for determining a resonant frequency of a wind turbine tower | |
| EP1298511A1 (en) | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis | |
| US6092029A (en) | Method and apparatus for diagnosing and controlling rotating stall and surge in rotating machinery | |
| US6587737B2 (en) | Method for the monitoring of a plant | |
| CN111272412B (en) | Fault detection method, device, equipment and storage medium of electric control pneumatic equipment | |
| CN110378042B (en) | Wind turbine generator gearbox oil temperature anomaly detection method and system based on SCADA data | |
| CN111811108B (en) | Heat exchanger filth blockage detection method and device | |
| CN111400961B (en) | Wind generating set blade fault judging method and device | |
| CN113657693B (en) | Predictive maintenance system and method for intelligent manufacturing equipment | |
| CN106089754A (en) | Immersible pump real-time fault diagnosis based on " the Internet+" and method for maintaining | |
| CN112347634A (en) | Wind generating set hydraulic variable pitch system fault prediction method based on SCADA system | |
| CN115033042B (en) | Intelligent control system of food dehydrator based on multi-mode Internet of things | |
| CN114723187A (en) | Intelligent tower crane, fault prediction method of intelligent tower crane and storage medium | |
| CN109779938B (en) | Intelligent interlocking protection method for centrifugal compressor unit | |
| CN112709690B (en) | Method, apparatus, device and medium for detecting fault of electrically driven compressor system | |
| CN109765786B (en) | Evidence filtering-based method for detecting imbalance fault of motor rotating shaft of electric ship | |
| CN109209781B (en) | The Fault Locating Method and device of wind power generating set | |
| CN115389247B (en) | Rotating machinery fault monitoring method based on speed self-adaptive encoder |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |